Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4777 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6412. Min Act: -0.0000

Data Index: 976250 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6572. Min Act: -0.0000

Data Index: 909191 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6332. Min Act: -0.0000

Data Index: 672707 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1316901 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5086. Min Act: -0.0000

Data Index: 592121 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5232. Min Act: -0.0000

Data Index: 700812 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4973. Min Act: -0.0000

Data Index: 788400 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5179. Min Act: -0.0000

Data Index: 460924 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4990. Min Act: -0.0000

Data Index: 750709 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1081732 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4883. Min Act: -0.0000

Data Index: 1263617 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4578. Min Act: -0.0000

Data Index: 921842 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4697. Min Act: -0.0000

Data Index: 364850 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1025744 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1157429 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1353966 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4247. Min Act: -0.0000

Data Index: 700609 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4264. Min Act: -0.0000

Data Index: 325439 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1301064 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4367. Min Act: -0.0000

Data Index: 698208 (C4 (Web Text))

Max Activating Token Index: 396